Artificial Intelligence for Contrast-Free MRI: Scar Assessment in Myocardial Infarction Using Deep Learning-Based Virtual Native Enhancement.

BACKGROUND: Myocardial scars are assessed noninvasively using cardiovascular magnetic resonance late gadolinium enhancement (LGE) as an imaging gold standard. A contrast-free approach would provide many advantages, including a faster and cheaper scan without contrast-associated problems. METHODS: Virtual native enhancement (VNE) is a novel technology that can produce virtual LGE-like images without the need for contrast. VNE combines cine imaging and native T1 maps to produce LGE-like images using artificial intelligence. VNE was developed for patients with previous myocardial infarction from 4271 data sets (912 patients); each data set comprises slice position-matched cine, T1 maps, and LGE images. After quality control, 3002 data sets (775 patients) were used for development and 291 data sets (68 patients) for testing. The VNE generator was trained using generative adversarial networks, using 2 adversarial discriminators to improve the image quality. The left ventricle was contoured semiautomatically. Myocardial scar volume was quantified using the full width at half maximum method. Scar transmurality was measured using the centerline chord method and visualized on bull's-eye plots. Lesion quantification by VNE and LGE was compared using linear regression, Pearson correlation (R), and intraclass correlation coefficients. Proof-of-principle histopathologic comparison of VNE in a porcine model of myocardial infarction also was performed. RESULTS: VNE provided significantly better image quality than LGE on blinded analysis by 5 independent operators on 291 data sets (all P<0.001). VNE correlated strongly with LGE in quantifying scar size (R, 0.89; intraclass correlation coefficient, 0.94) and transmurality (R, 0.84; intraclass correlation coefficient, 0.90) in 66 patients (277 test data sets). Two cardiovascular magnetic resonance experts reviewed all test image slices and reported an overall accuracy of 84% for VNE in detecting scars when compared with LGE, with specificity of 100% and sensitivity of 77%. VNE also showed excellent visuospatial agreement with histopathology in 2 cases of a porcine model of myocardial infarction. CONCLUSIONS: VNE demonstrated high agreement with LGE cardiovascular magnetic resonance for myocardial scar assessment in patients with previous myocardial infarction in visuospatial distribution and lesion quantification with superior image quality. VNE is a potentially transformative artificial intelligence-based technology with promise in reducing scan times and costs, increasing clinical throughput, and improving the accessibility of cardiovascular magnetic resonance in the near future.

Deep Learning-Based Segmentation and Uncertainty Assessment for Automated Analysis of Myocardial Perfusion MRI Datasets Using Patch-Level Training and Advanced Data Augmentation.

In this work, we develop a patch-level training approach and a task-driven intensity-based augmentation method for deep-learning-based segmentation of motion-corrected perfusion cardiac magnetic resonance imaging (MRI) datasets. Further, the proposed method generates an image-based uncertainty map thanks to a novel spatial sliding-window approach used during patch-level training, hence allowing for uncertainty quantification. Using the quantified uncertainty, we detect the out-of-distribution test data instances so that the end-user can be alerted that the test data is not suitable for the trained network. This feature has the potential to enable a more reliable integration of the proposed deep learning-based framework into clinical practice. We test our approach on external MRI data acquired using a different acquisition protocol to demonstrate the robustness of our performance to variations in pulse-sequence parameters. The presented results further demonstrate that our deep-learning image segmentation approach trained with the proposed data-augmentation technique incorporating spatiotemporal (2D+time) patches is superior to the state-of-the-art 2D approach in terms of generalization performance.

Assessment of intramyocardial hemorrhage with dark-blood T2*-weighted cardiovascular magnetic resonance.

BACKGROUND: Intramyocardial hemorrhage (IMH) within myocardial infarction (MI) is associated with major adverse cardiovascular events. Bright-blood T2*-based cardiovascular magnetic resonance (CMR) has emerged as the reference standard for non-invasive IMH detection. Despite this, the dark-blood T2*-based CMR is becoming interchangeably used with bright-blood T2*-weighted CMR in both clinical and preclinical settings for IMH detection. To date however, the relative merits of dark-blood T2*-weighted with respect to bright-blood T2*-weighted CMR for IMH characterization has not been studied. We investigated the diagnostic capacity of dark-blood T2*-weighted CMR against bright-blood T2*-weighted CMR for IMH characterization in clinical and preclinical settings. MATERIALS AND METHODS: Hemorrhagic MI patients (n = 20) and canines (n = 11) were imaged in the acute and chronic phases at 1.5 and 3 T with dark- and bright-blood T2*-weighted CMR. Imaging characteristics (Relative signal-to-noise (SNR), Relative contrast-to-noise (CNR), IMH Extent) and diagnostic performance (sensitivity, specificity, accuracy, area-under-the-curve, and inter-observer variability) of dark-blood T2*-weighted CMR for IMH characterization were assessed relative to bright-blood T2*-weighted CMR. RESULTS: At both clinical and preclinical settings, compared to bright-blood T2*-weighted CMR, dark-blood T2*-weighted images had significantly lower SNR, CNR and reduced IMH extent (all p < 0.05). Dark-blood T2*-weighted CMR also demonstrated weaker sensitivity, specificity, accuracy, and inter-observer variability compared to bright-blood T2*-weighted CMR (all p < 0.05). These observations were consistent across infarct age and imaging field strengths. CONCLUSION: While IMH can be visible on dark-blood T2*-weighted CMR, the overall conspicuity of IMH is significantly reduced compared to that observed in bright-blood T2*-weighted images, across infarct age in clinical and preclinical settings at 1.5 and 3 T. Hence, bright-blood T2*-weighted CMR would be preferable for clinical use since dark-blood T2*-weighted CMR carries the potential to misclassify hemorrhagic MIs as non-hemorrhagic MIs.

Retrospective assessment of at-risk myocardium in reperfused acute myocardial infarction patients using contrast-enhanced balanced steady-state free-precession cardiovascular magnetic resonance at 3T with SPECT validation.

BACKGROUND: Contrast-enhanced (CE) steady-state free precession (SSFP) CMR at 1.5T has been shown to be a valuable alternative to T2-based methods for the detection and quantifications of area-at-risk (AAR) in acute myocardial infarction (AMI) patients. However, CE-SSFP's capacity for assessment of AAR at 3T has not been investigated. We examined the clinical utility of CE-SSFP and T2-STIR for the retrospective assessment of AAR at 3T with single-photon-emission-computed tomography (SPECT) validation. MATERIALS AND METHODS: A total of 60 AMI patients (ST-elevation AMI, n = 44;  non-ST-elevation AMI, n = 16) were recruited into the CMR study between 3 and 7 days post revascularization. All patients underwent T2-STIR, CE-bSSFP and late-gadolinium-enhancement CMR. For validation, SPECT images were acquired in a subgroup of patients (n = 30). RESULTS: In 53 of 60 patients (88 %), T2-STIR was of diagnostic quality compared with 54 of 60 (90 %) with CE-SSFP. In a head-to-head per-slice comparison (n = 365), there was no difference in AAR quantified using T2-STIR and CE-SSFP (R2 = 0.92, p < 0.001; bias:-0.4 ± 0.8 cm2, p = 0.46). On a per-patient basis, there was good agreement between CE-SSFP (n = 29) and SPECT (R2 = 0.86, p < 0.001; bias: - 1.3 ± 7.8 %LV, p = 0.39) for AAR determination. T2-STIR also showed good agreement with SPECT for AAR measurement (R2 = 0.81, p < 0.001, bias: 0.5 ± 11.1 %LV, p = 0.81). There was also a strong agreement between CE-SSFP and T2-STIR with respect to the assessment of AAR on per-patient analysis (R2 = 0.84, p < 0.001, bias: - 2.1 ± 10.1 %LV, p = 0.31). CONCLUSIONS: At 3T, both CE-SSFP and T2-STIR can retrospectively quantify the at-risk myocardium with high accuracy.

Accurate needle-free assessment of myocardial oxygenation for ischemic heart disease in canines using magnetic resonance imaging.

Myocardial oxygenation-the ability of blood vessels to supply the heart muscle (myocardium) with oxygen-is a critical determinant of cardiac function. Impairment of myocardial oxygenation is a defining feature of ischemic heart disease (IHD), which is caused by pathological conditions that affect the blood vessels supplying oxygen to the heart muscle. Detecting altered myocardial oxygenation can help guide interventions and prevent acute life-threatening events such as heart attacks (myocardial infarction); however, current diagnosis of IHD relies on surrogate metrics and exogenous contrast agents for which many patients are contraindicated. An oxygenation-sensitive cardiac magnetic resonance imaging (CMR) approach used previously to demonstrate that CMR signals can be sensitized to changes in myocardial oxygenation showed limited ability to detect small changes in signals in the heart because of physiologic and imaging noise during data acquisition. Here, we demonstrate a CMR-based approach termed cfMRI [cardiac functional magnetic resonance imaging (MRI)] that detects myocardial oxygenation. cfMRI uses carbon dioxide for repeat interrogation of the functional capacity of the heart's blood vessels via a fast MRI approach suitable for clinical adoption without limitations of key confounders (cardiac/respiratory motion and heart rate changes). This method integrates multiple whole-heart images within a computational framework to reduce noise, producing confidence maps of alterations in myocardial oxygenation. cfMRI permits noninvasive monitoring of myocardial oxygenation without requiring ionizing radiation, contrast agents, or needles. This has the potential to broaden our ability to noninvasively identify IHD and a diverse spectrum of heart diseases related to myocardial ischemia.

Assessment of myocardial reactivity to controlled hypercapnia with free-breathing T2-prepared cardiac blood oxygen level-dependent MR imaging.

PURPOSE: To examine whether controlled and tolerable levels of hypercapnia may be an alternative to adenosine, a routinely used coronary vasodilator, in healthy human subjects and animals. MATERIALS AND METHODS: Human studies were approved by the institutional review board and were HIPAA compliant. Eighteen subjects had end-tidal partial pressure of carbon dioxide (PetCO2) increased by 10 mm Hg, and myocardial perfusion was monitored with myocardial blood oxygen level-dependent (BOLD) magnetic resonance (MR) imaging. Animal studies were approved by the institutional animal care and use committee. Anesthetized canines with (n = 7) and without (n = 7) induced stenosis of the left anterior descending artery (LAD) underwent vasodilator challenges with hypercapnia and adenosine. LAD coronary blood flow velocity and free-breathing myocardial BOLD MR responses were measured at each intervention. Appropriate statistical tests were performed to evaluate measured quantitative changes in all parameters of interest in response to changes in partial pressure of carbon dioxide. RESULTS: Changes in myocardial BOLD MR signal were equivalent to reported changes with adenosine (11.2% ± 10.6 [hypercapnia, 10 mm Hg] vs 12% ± 12.3 [adenosine]; P = .75). In intact canines, there was a sigmoidal relationship between BOLD MR response and PetCO2 with most of the response occurring over a 10 mm Hg span. BOLD MR (17% ± 14 [hypercapnia] vs 14% ± 24 [adenosine]; P = .80) and coronary blood flow velocity (21% ± 16 [hypercapnia] vs 26% ± 27 [adenosine]; P > .99) responses were similar to that of adenosine infusion. BOLD MR signal changes in canines with LAD stenosis during hypercapnia and adenosine infusion were not different (1% ± 4 [hypercapnia] vs 6% ± 4 [adenosine]; P = .12). CONCLUSION: Free-breathing T2-prepared myocardial BOLD MR imaging showed that hypercapnia of 10 mm Hg may provide a cardiac hyperemic stimulus similar to adenosine.

Assessment of regional myocardial oxygenation changes in the presence of coronary artery stenosis with balanced SSFP imaging at 3.0 T: theory and experimental evaluation in canines.

PURPOSE: To examine the dependence of steady-state free-precession (SSFP) -based myocardial blood-oxygen-level-dependent (BOLD) contrast on field strength using theoretical and experimental models. MATERIALS AND METHODS: Numerical simulations using a two-pool exchange model and a surgically prepared dog model were used to assess the SSFP-based myocardial BOLD signal changes at 1.5T and 3.0T. Experimental studies were performed in eight canines with pharmacological vasodilation under various levels of left circumflex coronary artery stenosis. Experimentally obtained BOLD signal changes were correlated against microsphere-based true flow changes. RESULTS: Theoretical results showed that, at 3.0T, relative to 1.5T, a threefold increase in oxygen sensitivity can be expected. Experimental studies in canines showed near similar results-a 2.5 +/- 0.2-fold increase in BOLD sensitivity at 3.0T relative to 1.5T (P < 0.05). Based on the scatter gram of BOLD data and microsphere data, it was found that the minimum regional flow difference that can be detected with SSFP-based myocardial BOLD imaging at 1.5T and 3.0T were 2.9 and 1.6, respectively (P < 0.05). CONCLUSION: This study demonstrated that SSFP-based myocardial BOLD sensitivity is substantially greater at 3.0T compared with 1.5T. The findings here suggest that SSFP-based myocardial BOLD imaging at 3.0T may have the necessary sensitivity to detect the clinically required minimum flow difference of 2.0.

On the parameters affecting the sensitivity of MR measures of pressure with microbubbles.

Recently, it has been suggested that gas encapsulated distensible microbubbles may serve as pressure probes in the MR field through the relationship between bubble size and 1/T(2) or 1/T(*)(2). Currently, in vivo application of this technique is hindered by the ability of T(2) or T(*)(2) to detect pressure changes that are clinically relevant. This work identifies and characterizes, through numerical simulations, the set of parameters which optimize the ability of this technique to detect small pressure changes. Results show that when the bubbles do not interact magnetically, the T(2)- and T(*)(2)-based measurements of pressure are strongly influenced by the bubble size at atmospheric pressure, static magnetic field strength, magnitude of the susceptibility difference between the encapsulated gas and plasma, bubble volume fraction, and the refocusing interval. In particular, to detect clinically relevant pressure changes, microbubbles need to be approximately 2-3 microm in radius, distributed at a volume fraction of 0.15%, and have a volumetric magnetic susceptibility difference of at least 34 ppm.